INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Rice is a vital staple crop that plays a crucial role in global food security. However, rice production is constantly threatened by various diseases, which can significantly reduce crop yields and quality. Early detection and accurate prediction of rice leaf diseases are essential for implementing effective control measures and minimizing crop losses. In recent years, deep learning techniques have shown promising results in disease prediction tasks. In this paper, we propose a novel approach for rice leaf disease prediction using a Capsule Neural Network (CapsNet). The CapsNet architecture represents a departure from traditional convolutional neural networks (CNNs) by incorporating the concept of capsules, which are dynamic routing units that capture spatial hierarchies in images. By leveraging the inherent structural information within rice leaf images, CapsNet offers enhanced representation learning capabilities compared to conventional CNNs, making it well-suited for disease prediction tasks. The proposed methodology involves several steps. Firstly, a comprehensive dataset comprising labeled rice leaf images is collected, encompassing different varieties of healthy leaves and various diseased conditions. These images are preprocessed to enhance features and remove noise, ensuring optimal input for the CapsNet model. The CapsNet is then trained using the dataset, employing an appropriate loss function and optimization algorithm. To evaluate the performance of the proposed approach, a series of experiments are conducted using cross-validation techniques. The results are compared against traditional CNN architectures, such as AlexNet and ResNet, as well as other state-of-the-art disease prediction models. Performance metrics including accuracy, precision, recall, and F1-score are employed to assess the effectiveness of the CapsNet model. The experimental results demonstrate that the proposed CapsNet-based approach achieves superior accuracy and robustness in rice leaf disease prediction compared to conventional CNN models. The model exhibits high sensitivity in detecting early signs of disease, enabling timely interventions to prevent further spread. The proposed approach holds significant potential for real-world applications in precision agriculture, aiding farmers in making informed decisions and implementing targeted disease management strategies
Keywords:
CapsNet, CNN, AlexNet, ResNet.
Cite Article:
"IDENTIFICATION AND ANALYSIS OF RICE LEAF DISEASE USING CAPSULE NEURAL NETWORK", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 7, page no.b581-b587, July-2023, Available :http://www.ijnrd.org/papers/IJNRD2307164.pdf
Downloads:
000118764
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn